SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

• URL: http://arxiv.org/abs/2311.02191v1
• Date: Fri, 3 Nov 2023 18:48:01 GMT
• Title: SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data
• Authors: Jose Luis Ponton, Haoran Yun, Andreas Aristidou, Carlos Andujar, Nuria Pelechano
• Abstract summary: We introduce SparsePoser, a novel deep learning-based solution for reconstructing a full-body pose from sparse data. Our system incorporates a convolutional-based autoencoder that synthesizes high-quality continuous human poses. We show that our method outperforms state-of-the-art techniques using IMU sensors or 6-DoF tracking devices.
• Score: 1.494051815405093
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate and reliable human motion reconstruction is crucial for creating natural interactions of full-body avatars in Virtual Reality (VR) and entertainment applications. As the Metaverse and social applications gain popularity, users are seeking cost-effective solutions to create full-body animations that are comparable in quality to those produced by commercial motion capture systems. In order to provide affordable solutions, though, it is important to minimize the number of sensors attached to the subject's body. Unfortunately, reconstructing the full-body pose from sparse data is a heavily under-determined problem. Some studies that use IMU sensors face challenges in reconstructing the pose due to positional drift and ambiguity of the poses. In recent years, some mainstream VR systems have released 6-degree-of-freedom (6-DoF) tracking devices providing positional and rotational information. Nevertheless, most solutions for reconstructing full-body poses rely on traditional inverse kinematics (IK) solutions, which often produce non-continuous and unnatural poses. In this article, we introduce SparsePoser, a novel deep learning-based solution for reconstructing a full-body pose from a reduced set of six tracking devices. Our system incorporates a convolutional-based autoencoder that synthesizes high-quality continuous human poses by learning the human motion manifold from motion capture data. Then, we employ a learned IK component, made of multiple lightweight feed-forward neural networks, to adjust the hands and feet toward the corresponding trackers. We extensively evaluate our method on publicly available motion capture datasets and with real-time live demos. We show that our method outperforms state-of-the-art techniques using IMU sensors or 6-DoF tracking devices, and can be used for users with different body dimensions and proportions.

Related papers

• Self-Avatar Animation in Virtual Reality: Impact of Motion Signals Artifacts on the Full-Body Pose Reconstruction [13.422686350235615]
  We aim to measure the impact on the reconstruction of the articulated self-avatar's full-body pose. We analyze the motion reconstruction errors using ground truth and 3D Cartesian coordinates estimated from textitYOLOv8 pose estimation.
  arXiv  Detail & Related papers  (2024-04-29T12:02:06Z)
• Universal Humanoid Motion Representations for Physics-Based Control [71.46142106079292]
  We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. We first learn a motion imitator that can imitate all of human motion from a large, unstructured motion dataset. We then create our motion representation by distilling skills directly from the imitator.
  arXiv  Detail & Related papers  (2023-10-06T20:48:43Z)
• Utilizing Task-Generic Motion Prior to Recover Full-Body Motion from Very Sparse Signals [3.8079353598215757]
  We propose a method that utilizes information from a neural motion prior to improve the accuracy of reconstructed user's motions. This is based on the premise that the ultimate goal of pose reconstruction is to reconstruct the motion, which is a series of poses.
  arXiv  Detail & Related papers  (2023-08-30T08:21:52Z)
• Physics-based Motion Retargeting from Sparse Inputs [73.94570049637717]
  Commercial AR/VR products consist only of a headset and controllers, providing very limited sensor data of the user's pose. We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies. We show that the avatar poses often match the user surprisingly well, despite having no sensor information of the lower body available.
  arXiv  Detail & Related papers  (2023-07-04T21:57:05Z)
• Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model [18.139630622759636]
  We present AGRoL, a novel conditional diffusion model specifically designed to track full bodies given sparse upper-body tracking signals. Our model is based on a simple multi-layer perceptron (MLP) architecture and a novel conditioning scheme for motion data. Unlike common diffusion architectures, our compact architecture can run in real-time, making it suitable for online body-tracking applications.
  arXiv  Detail & Related papers  (2023-04-17T19:35:13Z)
• QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars [80.05743236282564]
  Real-time tracking of human body motion is crucial for immersive experiences in AR/VR. We present a reinforcement learning framework that takes in sparse signals from an HMD and two controllers. We show that a single policy can be robust to diverse locomotion styles, different body sizes, and novel environments.
  arXiv  Detail & Related papers  (2022-09-20T00:25:54Z)
• AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing [24.053096294334694]
  We present AvatarPoser, the first learning-based method that predicts full-body poses in world coordinates using only motion input from the user's head and hands. Our method builds on a Transformer encoder to extract deep features from the input signals and decouples global motion from the learned local joint orientations. In our evaluation, AvatarPoser achieved new state-of-the-art results in evaluations on large motion capture datasets.
  arXiv  Detail & Related papers  (2022-07-27T20:52:39Z)
• Transformer Inertial Poser: Attention-based Real-time Human Motion Reconstruction from Sparse IMUs [79.72586714047199]
  We propose an attention-based deep learning method to reconstruct full-body motion from six IMU sensors in real-time. Our method achieves new state-of-the-art results both quantitatively and qualitatively, while being simple to implement and smaller in size.
  arXiv  Detail & Related papers  (2022-03-29T16:24:52Z)
• Learning Motion Priors for 4D Human Body Capture in 3D Scenes [81.54377747405812]
  We propose LEMO: LEarning human MOtion priors for 4D human body capture. We introduce a novel motion prior, which reduces the jitters exhibited by poses recovered over a sequence. We also design a contact friction term and a contact-aware motion infiller obtained via per-instance self-supervised training. With our pipeline, we demonstrate high-quality 4D human body capture, reconstructing smooth motions and physically plausible body-scene interactions.
  arXiv  Detail & Related papers  (2021-08-23T20:47:09Z)
• Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors [71.29186299435423]
  We introduce (HPS) Human POSEitioning System, a method to recover the full 3D pose of a human registered with a 3D scan of the surrounding environment. We show that our optimization-based integration exploits the benefits of the two, resulting in pose accuracy free of drift. HPS could be used for VR/AR applications where humans interact with the scene without requiring direct line of sight with an external camera.
  arXiv  Detail & Related papers  (2021-03-31T17:58:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.